Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bao, Ting, Mao, Ning, Duan, Wenhui, Xu, Yong, Del Maestro, Adrian, Zhang, Yang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.12452
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915114128506880
author Bao, Ting
Mao, Ning
Duan, Wenhui
Xu, Yong
Del Maestro, Adrian
Zhang, Yang
author_facet Bao, Ting
Mao, Ning
Duan, Wenhui
Xu, Yong
Del Maestro, Adrian
Zhang, Yang
contents The integration of density functional theory (DFT) with machine learning enables efficient \textit{ab initio} electronic structure calculations for ultra-large systems. In this work, we develop a transfer learning framework tailored for long-wavelength moiré systems. To balance efficiency and accuracy, we adopt a two-step transfer learning strategy: (1) the model is pre-trained on a large dataset of computationally inexpensive non-twisted structures until convergence, and (2) the network is then fine-tuned using a small set of computationally expensive twisted structures. Applying this method to twisted MoTe$_2$, the neural network model generates the resulting Hamiltonian for a 1000-atom system in 200 seconds, achieving a mean absolute error below 0.1 meV. To demonstrate $O(N)$ scalability, we model nanoribbon systems with up to 0.25 million atoms ($\sim9$ million orbitals), accurately capturing edge states consistent with predicted Chern numbers. This approach addresses the challenges of accuracy, efficiency, and scalability, offering a viable alternative to conventional DFT and enabling the exploration of electronic topology in large scale moiré systems towards simulating realistic device architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2501_12452
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transfer learning electronic structure: millielectron volt accuracy for sub-million-atom moiré semiconductor
Bao, Ting
Mao, Ning
Duan, Wenhui
Xu, Yong
Del Maestro, Adrian
Zhang, Yang
Materials Science
Strongly Correlated Electrons
The integration of density functional theory (DFT) with machine learning enables efficient \textit{ab initio} electronic structure calculations for ultra-large systems. In this work, we develop a transfer learning framework tailored for long-wavelength moiré systems. To balance efficiency and accuracy, we adopt a two-step transfer learning strategy: (1) the model is pre-trained on a large dataset of computationally inexpensive non-twisted structures until convergence, and (2) the network is then fine-tuned using a small set of computationally expensive twisted structures. Applying this method to twisted MoTe$_2$, the neural network model generates the resulting Hamiltonian for a 1000-atom system in 200 seconds, achieving a mean absolute error below 0.1 meV. To demonstrate $O(N)$ scalability, we model nanoribbon systems with up to 0.25 million atoms ($\sim9$ million orbitals), accurately capturing edge states consistent with predicted Chern numbers. This approach addresses the challenges of accuracy, efficiency, and scalability, offering a viable alternative to conventional DFT and enabling the exploration of electronic topology in large scale moiré systems towards simulating realistic device architectures.
title Transfer learning electronic structure: millielectron volt accuracy for sub-million-atom moiré semiconductor
topic Materials Science
Strongly Correlated Electrons
url https://arxiv.org/abs/2501.12452